Interpretable Machine Learning

As a staff research scientist at Google Brain, Been Kim focuses on interpretability–helping humans communicate with complex machine-learning models by not only building tools but also studying how humans interact with these systems.

In an interview, Kim discusses her path to AI/interpretability, interpretability and software testing, testing with concept activation vectors (TCAV) and its limitations, acquisition of chess knowledge in AlphaZero, and much more.

From The Gradient
View Full Article